Transform your applications and workflows into powerful agentic systems at global scale.
Gemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
Get Started Free
$300 Free Credits to Build on Google Cloud
New customers can spin up VMs, build with AI, and query data at no cost.
Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
Can you recover when it matters most? Take this quick assessment to identify gaps and build greater recovery confidence.
Is your recovery strategy as strong as you think? Take this quick self-assessment to check your recovery readiness and gain tailored insights. In only 2 minutes, you'll learn where you fall on the recovery readiness scale.
An implementation of the Memory Prediction Framework. For more information on memory prediction framework (aka HTM – Hierarchical Temporal Memory) go to http://www.numenta.com which is a company of Jeff Hawkins, the inventor of the theory.
Content Addressable Memory, Multi-Variate Statistics, Data Mining Includes analyzing datasets, extracting patterns, creating empirical expert system. Computes joint probabilities and implements a "belief" as the solution of an equilibrium equation
Todbot is an AI addon to the gamestool virtual machine. The aim is to create an evolving neural network topology that should be capable of creating the optimal topology and network weighting to solve any problem given it.
UCR is a project name for the development of an handwritten characters in Korean language. The goal is to create a UCR Library for handwriting as well as OCR from off-line, on-line data. And we have a plan to build a UCR library for mobile.
Simdist lets you harness the power of cluster computing without any knowledge of parallel libraries such as MPI, and with no restrictions on programming language. Primarily targeted at evolutionary computing and similar master-slave configurations.
Torch5 provides a matlab-like environment for state-of-the-art machine learning algorithms. It is easy to use and provides a very efficient implementation, thanks to a easy and fast scripting language (Lua) and a underlying C++ implementation.
The E* algorithm is a path planner for (mobile) robotics. Unlike A*, which constrains movements to graph edges, it produces smooth trajectories by interpolating between edges. Like D*, it supports dynamic replanning after local path cost changes.
general gambling - an extension to general game playing, providing non-determinism and partially observable information. GameMaster and games. Player is planned.
This project is an integration of the ALIVE framework, based on Organisational theory, into commercial games, providing game AI developers with tools to model gaming scenarios using social structures.
An adaptive neural network and evolutionary algorithms approach to the machine learning tasks, based on the modular graph grammars. Tested on the "two spirals problem" and other tasks.
Implemented in Matlab and C++.
Parallel Reinforcement Evolutionary Artificial Neural Networks (PREANN) is a framework of flexible multi-layer ANN's with reinforcement learning based on genetic algorithms and a parallel implementation (using XMM registers and NVIDIA's CUDA).
Toroid experiment is a try to create a model of life where animals evolving driving by genetic algorithms and each animal has it's own brain which is a neural network. For detailed description look at project page http://toroid-world.sourceforge.net
ManFieLd is an easy-to-use framework to develop filtering applications for Distributed System, relieving the burden of the developer to write the support code for the filtering methods.
The Tensor Voting Framework is a powerful technique for perceptual grouping, manifold learning, etc. It has proved to be a useful tool in the Computer Vision community. OpenTVF is an open source implementation of TVF.
The sourcecode of the Brainstormers' RoboCup champion team 2005 has been made publicly available at the end of 2005. That sourcecode release contains also a lot of our results in applying Reinforcement Learning in the simulated soccer domain.
Yann is Yet Another Neural Network. Yann is a library to create fast neural networks. It is also a GUI to easily create, edit, train, execute and investigate networks. Multiple topologies, runtime properties and ensemble learning are supported.
ROS repository for human-robot engagement package, developed at Worcester Polytechnic Institute. Currently contains ROS stack for recognizing and generating connection events. This work is supported by the NSF awards IIS-0811942 and IIS-1012083.